Skip to content

Marketplace

Everything your AI needs, in one place.

Ready-made agents, skills, personas, prompts, templates and tools. Each one is checked before it goes live, works with any model, and installs in a click. Rate what you use so the best rises to the top.

143.8K
listings
1
installs
0
reviews
38.7K
publishers
33 results
Skill

faster-whisper

Local speech-to-text using faster-whisper. 4-6x faster than OpenAI Whisper with identical accuracy; GPU acceleration enables ~20x realtime transcription. Supports standard and distilled models with wo

by sundial-orgskills.sh
Not rated yet
Free
Skill

modal-serverless-gpu

Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scal

by davila7skills.sh
Not rated yet
Free
Skill

skypilot-multi-cloud-orchestration

Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or opti

by davila7skills.sh
Not rated yet
Free
Skill

cupynumeric-install

Install and verify cuPyNumeric for Python — requirements, commands, verification. Source builds are out of scope.

by nvidiaskills.sh
Not rated yet
Free
Skill

cupynumeric-migration-readiness

Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNume

by nvidiaskills.sh
Not rated yet
Free
Skill

cupynumeric-parallel-data-load

Load a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a manual partition + leaf @task launch with CPU/OMP/G

by nvidiaskills.sh
Not rated yet
Free
Skill

deepstream-sop

Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators pe

by nvidiaskills.sh
Not rated yet
Free
Skill

jetson-customize-clocks

Use to lock/cap Jetson CPU/GPU/EMC clocks, toggle EMC/CPU DVFS, or change cpufreq governors by editing BPMP DTB and nvpower.sh pre-flash. Do NOT use for live tuning or nvpmodel edits.

by nvidiaskills.sh
Not rated yet
Free
Skill

portfolio-optimization

Use when a user asks to build, optimize, backtest, rebalance, or analyze a stock portfolio with Mean-CVaR, Mean-Variance/SOCP variance caps, efficient frontiers, scenario generation, or NVIDIA cuOpt.

by nvidiaskills.sh
Not rated yet
Free
Skill

tao-run-on-brev

Brev managed GPU instances with Docker support. Use when running TAO training, evaluation, or inference on Brev GPU instances, managing Brev deployments, or dispatching TAO jobs through the Brev CLI.

by nvidiaskills.sh
Not rated yet
Free
Skill

tao-run-on-kubernetes

Kubernetes execution platform — submits TAO container jobs as single-pod k8s Jobs with NVIDIA GPU scheduling. Use when running on EKS / GKE / AKS / on-prem clusters with the NVIDIA GPU Operator instal

by nvidiaskills.sh
Not rated yet
Free
Skill

tilegym-adding-cutile-kernel

Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark in tests/benchmark. Use when a

by nvidiaskills.sh
Not rated yet
Free
Skill

tilegym-converting-cutile-to-julia

Converts cuTile Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents. Handles kernel syntax translation, 0-indexed to 1-indexed conversion, broadcasting differences, memory layout (row-major

by nvidiaskills.sh
Not rated yet
Free
Skill

tilegym-converting-cutile-to-triton

Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch, numerical mismatch), and mapping cuTile idiom

by nvidiaskills.sh
Not rated yet
Free
Skill

warp-compile-time-optimizer

Use when compile time or startup time is the problem in code that uses Warp: a request to improve, optimize, or cut compile times; an app that is slow to start or stalls at the first wp.launch; second

by nvidiaskills.sh
Not rated yet
Free
Skill

modal-serverless-gpu

Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scal

by orchestra-researchskills.sh
Not rated yet
Free
Skill

skypilot-multi-cloud-orchestration

Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or opti

by orchestra-researchskills.sh
Not rated yet
Free
Skill

faster-whisper

Local speech-to-text using faster-whisper. 4-6x faster than OpenAI Whisper with identical accuracy; GPU acceleration enables ~20x realtime transcription. SRT/VTT/TTML/CSV subtitles, speaker diarizatio

by theplasmakskills.sh
Not rated yet
Free
Skill

accelerated-computing-cudf

Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.

by practicalswanskills.sh
Not rated yet
Free
Skill

autoresearch

Run Karpathy-style autonomous ML search on a real training repo: choose the right mode (setup, program.md, bounded loop, results interpretation, or constrained-hardware adaptation), preserve the immut

by akillnessskills.sh
Not rated yet
Free
Skill

metal-shader-expert

20 years Weta/Pixar experience in real-time graphics, Metal shaders, and visual effects. Expert in MSL shaders, PBR rendering, tile-based deferred rendering (TBDR), and GPU debugging. Activate on 'Met

by curiositechskills.sh
Not rated yet
Free
Skill

hashcat

GPU-accelerated password hash recovery with hashcat. Use when a user asks to crack NTLM/bcrypt/MD5/SHA/WPA hashes, run mask or rule-based attacks, convert a PCAP to a crackable hash, or benchmark hash

by terminalskillsskills.sh
Not rated yet
Free
Skill

pytorch

Assists with building, training, and deploying neural networks using PyTorch. Use when designing architectures for computer vision, NLP, or tabular data, optimizing training with mixed precision and d

by terminalskillsskills.sh
Not rated yet
Free
Skill

vllm

You are an expert in vLLM, the high-throughput LLM serving engine. You help developers deploy open-source models (Llama, Mistral, Qwen, Phi, Gemma) with PagedAttention for efficient memory management,

by terminalskillsskills.sh
Not rated yet
Free
1

Find

Search or browse by kind. Every card shows who made it, how many people installed it and what they think.

2

Install

One click. You get a manifest the router understands, plus copy-paste snippets for the CLI, Python and YAML.

3

Rate and publish

Leave a star rating after you have used it. Made something useful? Publish it - free listings go live immediately.

Prefer the terminal? osr stack apply registry://starter installs the starter template.